Fernando Carneiro commited on
Commit
4b7c77a
1 Parent(s): f5344ed

First commit

Browse files
Files changed (4) hide show
  1. bpe.codes +0 -0
  2. special_tokens_map.json +1 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +0 -0
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "tokenizer_class": "BertweetTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff